Efficient Low-resolution Character Recognition Using Sub-machine-code Genetic Programming
The paper describes an approach to low-resolution character recognition for real-time applications based on a set of binary classifiers designed by means of Sub-machine-code Genetic Programming (SmcGP). SmcGP is a type of GP that interprets long integers as bit strings to achieve SIMD processing on traditional sequential computers. The method was tested on an extensive set of very low-resolution binary patterns (of size 13 × 8 pixels) that represent digits from 0 to 9. Ten binary classifiers were designed, each corresponding to a pattern class. In case of no response by any of the classifiers, a reference LVQ classifier was used. The paper compares the resulting classifier with a reference classifier, showing an almost 10-fold improvement in speed, at the price of a slightly lower accuracy.
KeywordsGenetic Programming Input Pattern Binary Classifier Optical Character Recognition License Plate
Unable to display preview. Download preview PDF.
- 2.W.Banzhaf, F.Francone, J.Keller, and P.Nordin. Genetic Programming: An Introduction. Morgan Kaufmann, 1998.Google Scholar
- 3.R.Poli and W.B Langdon. Sub-machine-code Genetic Programming In L.Spector, U.M.O’Reilly W.B.Langdon, and P.J.Angeline, editors, Advances in Genetic Programming 3, chapter 13, pages 301–323. MIT Press, 1999.Google Scholar
- 4.R.Poli. Sub-machine-code GP:New results and extensions. In W.B.Langdon R.Poli, P.Nordin and T.Fogarty, editors, Proceedings of the Second European Workshop on Genetic Programming - EuroGP’99, number 1598 in Lecture Notes on Computer Science, pages 65–82. Springer Verlag, 1999.Google Scholar
- 5.G.Adorni, F.Bergenti, S.Cagnoni, and M.Mordonini. License-plate recognition for restricted-access area control systems. In G.L.Foresti, P.Mähönen, and C.S.Regazzoni, editors, Multimedia Video-Based Surveillance Systems: Requirements, Issues and Solutions. Kluwer, 2000.Google Scholar
- 6.G.Adorni, S.Cagnoni, M.Gori, and M.Mordonini. Access control system with neuro-fuzzy supervision. In Proc. of the Intelligent Transportation Systems Conference (ITSC2001), pages 472–477, 2001.Google Scholar
- 8.S.Cagnoni and G.Valli. OSLVQ: a training strategy for optimum-size Learning Vector Quantization classifiers. In Proc. of the 1st IEEE World Conference on Computational Intelligence: ICNN94, pages 762–765, June 1994.Google Scholar
- 9.J.A.G. Nijhuis, M.H. ter Brugge, K.A. Helmolt, J.P.W. Pluim, L.Spaanenburg, R.S. Venema, and M.A. Westenberg. Car license plate recognition wiht neural networks and fuzzy logic. In Proc. IEEE Int’l Conf. on Neural Networks, volume 5, pages 2232–2236, 1995.Google Scholar
- 10.N.Parker, J.Weeks, and R.Wilson, editors. Registration plates of the world. Europlate, 3rd edition, 1995.Google Scholar
- 12.D.Zongker and B.Punch. lil-gp 1.01 user’s manual. Michigan State University, 1996, available via anonymous ftp from ftp://garage.cse.msu.edu/pub/GA/lilgp. Google Scholar
- 13.J.P. Egan. Signal Detection Theory and R.O.C. Analysis. Academic Press, New York, 1975.Google Scholar
- 14.G.Adorni, F.Bergenti, and S.Cagnoni. A cellular-programming approach to pattern classification. In W.Banzhaf, R.Poli, M.Schoenauer, and T.C. Fogarty, editors, Proceedings of the First European Workshop on Genetic Programming(EuroGP98), number 1391 in Lecture Notes on Computer Science, pages 142–150, Springer-Verlag, 1998.Google Scholar